Measuring public knowledge on nuclear weapons in the post-Cold War: dimensionality and measurement invariance across eight European countries

Table 3 Fit indexes for invariance tests, 2018

	χ²	df	CFI	RMSEA	SRMR
Configural	573.7	256	0.987	0.039	0.049
Panel A: measurement invariance, latent variate scales unconstrained (except in the reference group)
A1. Thresholds and loadings	569.7	249	0.987	0.040	0.049
A2. + Intercepts	662.5	291	0.985	0.039	0.050
Panel B: measurement invariance, latent variate scales fixed across groups
B1. Thresholds and loadings	568.5	319	0.990	0.031	0.057
B2. + Intercepts	676.1	361	0.987	0.033	0.057
Panel C: structural invariance, latent variate scales fixed across groups
C1. Variances: general and specific, constrained to unit	1012.5	389	0.975	0.044	0.080
C2. Variances: general released, specific constrained to unit	724.1	382	0.986	0.033	0.059
C3. + Means: general and specific constrained to zero	1702.7	410	0.948	0.062	0.059
C4. + Means: general factor released, specific fixed to zero	1263.7	403	0.965	0.051	0.059

Note: All models are estimated using unweighted least squares estimator with mean- and variance-adjusted test statistics. Models use delta parameterization. χ²chi-squared test statistics, df degrees of freedom, CFI comparative fit index, RMSEA root mean square error of approximation, SRMR standardized root mean square residual

ISSN: 2523-8930